Align model card text with the corrected paper

Text only; no metric changed. New paper title and co-author name in the citation; QA scores described as development-split results; pretraining-data statement corrected; loss/perplexity pairing clarified.

README.md

@@ -125,8 +125,9 @@ for p, w in zip(pred, enc.word_ids(0)):
   languages, domains or label schemes is not characterised.
 - The base model covers Amharic and Tigrinya; other Ge'ez-script languages were
   not part of pretraining.
-- Corpora are drawn largely from religious and news domains, and the model may
-  reflect those distributions and any biases in them.
+- The pretraining text is of undocumented origin (licence unknown); samples contain religious
+  translations alongside general web prose, and the model may reflect those distributions
+  and any biases present in them.
 - Single-configuration study: no hyperparameter search was performed, and
   baseline comparisons in the paper are single-seed.
 
@@ -144,9 +145,9 @@ python3 evaluation/export_spm_results.py    # regenerates the metrics table
 
 ```bibtex
 @inproceedings{teklehaymanot2026vexmlm,
-  title     = {Expanding the Lexicon of Ge'ez Based African Languages:
-               A Comparative Study of Amharic and Tigrinya},
-  author    = {Teklehaymanot, Hailay Kidu and Yadeta, Gebregziabihier and
+  title     = {Vocabulary Expansion for Low-Resource African Languages:
+               A Case Study in Amharic and Tigrinya},
+  author    = {Teklehaymanot, Hailay Kidu and Yadeta, Debela Desalegn and
                Nejdl, Wolfgang},
   booktitle = {Proceedings of the Workshop on Language Models for
                Underserved Communities (LM4UC) at IJCAI},